A kinematic-based technique for the estimation of the times at which gait events occur is presented. A kinematic-based model (KM) is defined by the trajectory of a point, which has an anatomically fixed location on the subject's body, about a time at which a measurement system defined gait event takes place. The times at which subsequent occurrences of the gait event takes place are determined by identifying the kinematic pattern that best fits the previously defined KM. The results of an experiment that used the gait patterns of a normal and a pathological walker indicate that the accuracy of the algorithm is limited by the kinematic data sampling interval and that optimal kinematic predictors of gait event times occur within the primary (sagittal) plane of motion. The technique is intended to obviate the need for multiple force plates, instrumented floors and instruments which are worn by the subject for the purpose of determining the times at which gait events occur.

No abstract

Even though social networks can provide free space for discussing ideas, people can also use them to propagate hate speech and, given the amount of written material in such networks, it becomes necessary to rely on automatic methods for identifying this problem. In this work, we set out to verify the use of some classic Machine Learning algorithms for the task of hate speech detection in tweets written in Portuguese, by testing four different models (SVM, MLP, Logistic Regression and Naïve Bayes) with different configurations. Results show that these algorithms produce better results (in terms of micro-averaged F1 score) than the LSTM used for benchmark, being also competitive to other results by the related literature

No abstract